System and method for structuring speech recognized text into a pre-selected document format

Abstract

A system for creating a structured report using a template having at least one predetermined heading and formatting data associated with each heading. The steps include recording a voice file, creating a speech recognized text file corresponding to the voice file, identifying the location of each heading in the text file, and the text corresponding thereto, populating the template with the identified text corresponding to each heading, and formatting the populated template to create the structured report.

Description

RELATED APPLICATIONS[0001]This application is a continuation of U.S. application Ser. No. 10 / 375,045, entitled “SYSTEM AND METHOD FOR STRUCTURING SPEECH RECOGNIZED TEXT INTO A PRE-SELECTED DOCUMENT FORMAT” filed on Feb. 28, 2003, which is herein incorporated by reference in its entirety.BACKGROUND OF INVENTION[0002]The present invention relates generally to structuring, correcting, and formatting speech recognized text.[0003]Today's speech recognition technology enables a computer to transcribe spoken words into computer recognized text equivalents. Speech recognition is the process of converting an acoustic signal, captured by a transducive element, such as a microphone or a telephone, to a set of words. These words can be used for numerous applications including data entry and word processing. The development of speech recognition technology has traditionally focused on accurate speech recognition, which has been a formidable task due to the wide variety of pronunciations, individ...

AI Technical Summary

Benefits of technology

"The present invention is a speech recognition correction system that automatically creates a structured report. This system reduces the number of man-hours required to correct speech recognized text used for generating standard reports. The steps include creating a template with a user-defined format, selecting a voice file and a corresponding speech recognized text file, identifying the location of each heading in the text file, and the text corresponding thereto, and populating the template with the identified text corresponding to each heading. The system also includes a two-phase identifying step, with an automatic correction phase and a manual correction phase. The populated template is then converted into a word processing file, which is then formatted into a final report. The system can also include formatting data that corresponds to each heading and can be automatically applied to each heading and corresponding text section in the word processing file. The invention provides a significant need for a speech recognition correction system that automatically creates a structured report."

Problems solved by technology

Even with this improved speech recognition software, a transcriber or correctionist is often still necessary to correct mistakes.

Images